dat <- read.csv("data/evolucion_gripe_covid.csv")
gripe <- ts(dat$sdgripal, start=c(2020, 40), frequency=52)
result_gripe <- auto.fit.arima(gripe, plot_result = TRUE)
------------------------------------------------------------------------------------------
Series: serie
ARIMA(2,0,1) with non-zero mean
Coefficients:
ar1 ar2 ma1 mean
1.7011 -0.8606 -0.7378 233.5599
s.e. 0.1023 0.0832 0.1715 10.7434
sigma^2 = 2245: log likelihood = -299.83
AIC=609.66 AICc=610.83 BIC=619.87
------------------------------------------------------------------------------------------
Falla la hipótesis de normalidad sobre los residuos.
El modelo es válido pero los intervalos de predicción basados en la
dist. asintótica no son válidos
------------------------------------------------------------------------------------------
| MODELO FINAL |
------------------------------------------------------------------------------------------
Series: serie
ARIMA(2,0,1) with non-zero mean
Coefficients:
ar1 ar2 ma1 mean
1.7011 -0.8606 -0.7378 233.5599
s.e. 0.1023 0.0832 0.1715 10.7434
sigma^2 = 2245: log likelihood = -299.83
AIC=609.66 AICc=610.83 BIC=619.87
result_gripe$fig_serie <- result_gripe$fig_serie %>% layout(width=840, height=700)
result_gripe$fig_serie